Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
41
datasets available to search
ShareScore release 0.9.0
Dataset results
41 results for “Training samples”
2d U-net models trained to segment human placental maternal/fetal blood volumes and blood vessels from syncrotron micro-CT data along with a sample data volume.
<p>This dataset contains a 512 x 512 x 512 pixel volume taken from an imaging dataset of human placental tissue collected at Diamond Light Source Manchester Imaging Branchline, I13-2 on visits MG23941 and MG22562 using in-line high-resolution synchrotron-sourced phase contrast micro-computed X-ray tomography. This data is saved in HDF5 format with a uint8 datatype. Alongside this are two 2d binary U-net models that have been trained to segment this data. One model segments the data into regions of maternal/fetal blood volume, the other segments the blood vessels. Both models were trained using the fastai python package, which utilises the pytorch library. These models were used to segment the data in our paper "A massively multi-scale approach to characterising tissue architecture by synchrotron micro-CT applied to the human placenta" which can be found at <a href="https://www.biorxiv.org/content/10.1101/2020.12.07.411462v1">https://www.biorxiv.org/content/10.1101/2020.12.07.411462v1</a>. The code used for training the U-net models and for predicting the segmentation of the data volume can be found at <a href="https://github.com/DiamondLightSource/placental-segmentation-2dunet">https://github.com/DiamondLightSource/placental-segmentation-2dunet</a> and is published at <a href="https://doi.org/10.5281/zenodo.4252562">https://doi.org/10.5281/zenodo.4252562</a> </p>
Glassware images and code samples for training and identification of glassware by neural networks
<p>These images were used to perform an image identification exercise with first-year students in the author's Introduction to Scientific Computing course. The zip file also includes sample Mathematica notebooks that were used to perform the training and data analysis of the neural network's performance. The corresponding publication in the Journal of Computational Science Education can be found here <a href="https://doi.org/10.22369/issn.2153-4136/12/1/2">https://doi.org/10.22369/issn.2153-4136/12/1/2</a></p>
Netflow data without sampling for training (D1)
<p>NetFlow traffic generated using <strong>DOROTHEA</strong> (<strong>DO</strong>cker-based f<strong>R</strong>amework f<strong>O</strong>r ga<strong>TH</strong>ering n<strong>E</strong>tflow tr<strong>A</strong>ffic)</p> <p>NetFlow is a network protocol developed by Cisco for the collection and monitoring of network traffic flow data generated. A flow is defined as a unidirectional sequence of packets with some common properties that pass through a network device.</p> <p>NetFlow flows have been captured without sampling at the packet level. A sampling means that 1 out of every X packets is selected to be flow while the rest of the packets are not valued.</p> <p>The version of NetFlow used to build the datasets is 5.</p> <p>In the construction of the datasets, different percentages of flows considered attacks and flows considered normal traffic have been used.</p> <p>These datasets have been used to train machine learning models.</p>
Training dataset: Mass spectrometry based proteomics of healthy human serum samples
<p>The two raw files serve as a concise but meaningful training data set in the Galaxy training network (https://galaxyproject.github.io/training-material/).</p> <p>Serum of a healthy person was obtained by centrifugation of full blood in a serum-gelmonovette. One serum sample was depleted for high abundant proteins, the other not.<br> For the non-depleted sample: 5µl of serum was diluted with 0.1% Rapigest, resulting in a concentration of 1mg/ml.<br> Depletion was performed with the Seppro IgY14 Spin columns which are able to deplete 14 high abundent blood proteins by immunoaffinity. For the depleted sample 9µl of serum was diluted with TBS/HCl/NaCl buffer and added to the Seppro IgY14 spin column. After depletion the sample was buffered with Hepes pH 8.0 and Rapigest was added to a final 0.1% Rapigest concentration. From here on, both samples were reduced by adding TCEP, alkylated by IAA and quenched with DTT in solution. Digestion was performed by adding trypsin in a ratio of 1:50 to the samples. After incubation at 37°C, 600rpm, over night, the sample clean-up was performed with the PreOmics desalting columns. iRT peptides were added and the sample was measured with a Q-Exactive Plus mass spectrometer. Besides the two raw files, we uploaded a fasta file that serves as human protein sequence database and the Galaxy MaxQuant training result files: protein groups, peptides, mqpar and PTXQC.</p>
Large-Scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant - Datasets, Trained Models, BNN Samples, and MCMC Chains
<p>We publish the training/validation/test datasets, trained model weights, configuration files, Bayesian neural network samples, and MCMC chains used to produce the figures in the LSST DESC paper, "Large-Scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant." They are formatted to be used with the DESC package "H0rton" (<a href="https://github.com/jiwoncpark/h0rton">https://github.com/jiwoncpark/h0rton</a>). Additional descriptions can be found in the README. Please contact Ji Won Park (@jiwoncpark) on GitHub or <a href="https://github.com/jiwoncpark/h0rton/issues">make an issue</a> for any questions.</p>
Improving Algorithm-Selectors and Performance-Predictors via Learning Discriminating Training Samples - Code and Data
<p>This repository contains the code and data for reproducibility of the paper 'Improving Algorithm-Selectors and Performance-Predictors via Learning Discriminating Training Samples'. </p> <p>The following files are included:</p> <ul> <li>Plots: Additional plots not in the paper;</li> <li>Code: Python scripts to generate trajectories and perform classification/regression;</li> <li>best_algo.csv : Labels for the classification;</li> <li>performances.csv : Performances used for the regression;</li> <li>SA_parameters.csv : SA parameters for all machine learning tasks;</li> <li>irace_scenario.txt : scenario used for the tuning.</li> </ul>
Audio samples from generative models trained on the TIMIT speech data.
<p>This is a posting of audio snippets to accompany the paper "Benchmarking Generative Latent Variable Models for Speech".</p> <p>The snippets include samples and reconstructions. All samples are completely unconditional and utilise only the prior internal representations learned by the model. Reconstructions are computed from a given test audio snippet by first encoding it to a learned representation and then decoding that to a reconstruction of the audio.</p> <p>All models are trained on the TIMIT speech dataset (<a href="https://catalog.ldc.upenn.edu/LDC93s1">https://catalog.ldc.upenn.edu/LDC93s1</a>). Some snippets are from models trained at different temporal resolutions denoted by `s1` and `s64`. We refer to the paper for details.</p> <p>The files include:</p> <ul> <li>`clockwork-vae-s64-reconstruction-*` <ul> <li>Four reconstructions using a two-layered Clockwork VAE trained with temporal resolution s=64.</li> </ul> </li> <li>`clockwork-vae-s64-sample-*` <ul> <li>Four samples from the prior of a Clockwork VAE trained with temporal resolution s=64.</li> </ul> </li> <li>`original-*` <ul> <li>Four original samples from TIMIT corresponding in pairs to the reconstructions.</li> </ul> </li> <li>`vrnn-s64-sample-*` <ul> <li>Two samples from the prior of a VRNN trained with temporal resolution s=64.</li> </ul> </li> <li>`vrnn-s1-sample-*` <ul> <li>Two samples from the prior of a VRNN trained with temporal resolution s=1.</li> </ul> </li> <li>`srnn-s64-sample-*` <ul> <li>Two samples from the prior of a SRNN trained with temporal resolution s=64.</li> </ul> </li> <li>`srnn-s1-sample-*` <ul> <li>Two samples from the prior of a SRNN trained with temporal resolution s=1.</li> </ul> </li> <li>`wavenet-s64-sample-*` <ul> <li>Four samples from a WaveNet trained with temporal resolution s=1.</li> </ul> </li> <li>`wavenet-s1-sample-*` <ul> <li>Two samples from a WaveNet trained with temporal resolution s=64.</li> </ul> </li> </ul>
Netflow data with sampling 500 for training (D2)
<p>NetFlow traffic generated using DOROTHEA (DOcker-based fRamework fOr gaTHering nEtflow trAffic) NetFlow is a network protocol developed by Cisco for the collection and monitoring of network traffic flow data generated. A flow is defined as a unidirectional sequence of packets with some common properties that pass through a network device.</p> <p>NetFlow flows have been captured with sampling 500 at the packet level. A sampling means that 1 out of every X packets is selected to be flow while the rest of the packets are not valued.</p> <p>The version of NetFlow used to build the datasets is 5.</p>
Netflow data with sampling 250 for training (D1)
<p>NetFlow traffic generated using DOROTHEA (DOcker-based fRamework fOr gaTHering nEtflow trAffic) NetFlow is a network protocol developed by Cisco for the collection and monitoring of network traffic flow data generated. A flow is defined as a unidirectional sequence of packets with some common properties that pass through a network device.</p> <p>NetFlow flows have been captured with sampling 250 at the packet level. A sampling means that 1 out of every X packets is selected to be flow while the rest of the packets are not valued.</p> <p>The version of NetFlow used to build the datasets is 5.</p>
Netflow data with sampling 1000 for training (D3)
<p>NetFlow traffic generated using DOROTHEA (DOcker-based fRamework fOr gaTHering nEtflow trAffic) NetFlow is a network protocol developed by Cisco for the collection and monitoring of network traffic flow data generated. A flow is defined as a unidirectional sequence of packets with some common properties that pass through a network device.</p> <p>NetFlow flows have been captured with sampling 1000 at the packet level. A sampling means that 1 out of every X packets is selected to be flow while the rest of the packets are not valued.</p> <p>The version of NetFlow used to build the datasets is 5.</p>
Point sample database with spatial holdbacks for global forest edge model training
<p>Global point dataset sampling 50 biophysical parameters to train the global forest carbon edge model at https://github.com/springinnovate/carbon_edge_model/releases/tag/1.2.0</p> <p>Field schema:</p> <p>accessibility_to_cities_2015_30sec_compressed (Integer64)<br> altitude_10sec_compressed (Integer64)<br> baccini_carbon_data_2014_compressed (Integer64)<br> bio_01_30sec_compressed (Real)<br> bio_02_30sec_compressed (Real)<br> bio_03_30sec_compressed (Real)<br> bio_04_30sec_compressed (Real)<br> bio_05_30sec_compressed (Real)<br> bio_06_30sec_compressed (Real)<br> bio_07_30sec_compressed (Real)<br> bio_08_30sec_compressed (Real)<br> bio_09_30sec_compressed (Real)<br> bio_10_30sec_compressed (Real)<br> bio_11_30sec_compressed (Real)<br> bio_12_30sec_compressed (Real)<br> bio_13_30sec_compressed (Real)<br> bio_14_30sec_compressed (Real)<br> bio_15_30sec_compressed (Real)<br> bio_16_30sec_compressed (Real)<br> bio_17_30sec_compressed (Real)<br> bio_18_30sec_compressed (Real)<br> bio_19_30sec_compressed (Real)<br> cec_0-5cm_mean_compressed (Integer64)<br> cec_5-15cm_mean_compressed (Integer64)<br> cfvo_0-5cm_mean_compressed (Integer64)<br> cfvo_5-15cm_mean_compressed (Integer64)<br> clay_0-5cm_mean_compressed (Integer64)<br> clay_5-15cm_mean_compressed (Integer64)<br> fc_stack_hansen_forest_cover2014_compressed (Integer64)<br> gf_0.4_masked_forest_ESACCI-LC-L4-LCCS-Map-300m-P1Y-2014-v2.0.7 (Real)<br> gf_1.45_masked_forest_ESACCI-LC-L4-LCCS-Map-300m-P1Y-2014-v2.0.7 (Real)<br> gf_5.0_fc_stack_hansen_forest_cover2014_compressed (Real)<br> gf_5.0_masked_forest_ESACCI-LC-L4-LCCS-Map-300m-P1Y-2014-v2.0.7 (Real)<br> hillshade_10sec_compressed (Integer64)<br> masked_forest_ESACCI-LC-L4-LCCS-Map-300m-P1Y-2014-v2.0.7 (Integer64)<br> night_lights_10sec_compressed (Real)<br> night_lights_5min_compressed (Real)<br> nitrogen_0-5cm_mean_compressed (Integer64)<br> nitrogen_10sec_compressed (Integer64)<br> nitrogen_5-15cm_mean_compressed (Integer64)<br> phh2o_0-5cm_mean_compressed (Integer64)<br> phh2o_5-15cm_mean_compressed (Integer64)<br> sand_0-5cm_mean_compressed (Integer64)<br> silt_0-5cm_mean_compressed (Integer64)<br> silt_5-15cm_mean_compressed (Integer64)<br> slope_10sec_compressed (Real)<br> soc_0-5cm_mean_compressed (Integer64)<br> soc_5-15cm_mean_compressed (Integer64)<br> tri_10sec_compressed (Real)<br> wind_speed_10sec_compressed (Real)</p>
Training data for the "Computational textural mapping harmonises sampling variation and reveals multidimensional histopathological fingerprints"
<p>There are two ZIP-files consisting of small histological image tiles that have been used to detect and quantify distinct tissue textures and lymphocyte proportions from H&E-stained clear cell renal cell carcinoma (KIRC) digital tissue sections of the Cancer Genome Atlas (TCGA) image archive and the Helsinki dataset.</p> <p>The <strong>tissue_classification </strong>file contains 300x300px tissue texture image tiles (n=52,713) representing renal cancer (“cancer”; n=13,057, 24.8%); normal renal (“normal”; n=8,652, 16.4%); stromal (“stroma”; n= 5,460, 10.4%) including smooth muscle, fibrous stroma and blood vessels; red blood cells (“blood”; n=996, 1.9%); empty background (“empty”; n=16,026, 30.4%); and other textures including necrotic, torn and adipose tissue (“other”; n=8,522, 16.2%). Image tiles have been randomly selected from the TCGA-KIRC WSI and the Helsinki datasets.</p> <p>The <strong>binary_lymphocytes </strong>file contains mostly 256x256px-sized but also smaller image tiles of Low (n=20,092, 80.1%) or High (n=5,003, 19.9%) lymphocyte density (n=25,095). Image tiles have been randomly selected from the TCGA-KIRC WSI dataset.</p> <p>All accuracy of all annotations have been double-checked. However, the classification between multiple tissue textures or lymphocyte density can be sometimes ambiguous.</p> <p>The deep learning model parameters trained with the ResNet-18 infrastructure for (1) lymphocyte and (2) texture classification are named as (1) <strong>resnet18_binary_lymphocytes.pth</strong> and (2) <strong>resnet18_tissue_classification.pth</strong>. Codes and instructions to use these are found in <a href="https://github.com/vahvero/RCC_textures_and_lymphocytes_publication_image_analysis">https://github.com/vahvero/RCC_textures_and_lymphocytes_publication_image_analysis</a>.</p> <p> </p> <p>If you use either work, please cite the publication by Brummer O et al (1) AND the TCGA Research Network (2):<br><strong>(1) </strong><strong>Brummer, O., Pölönen, P., Mustjoki, S. <em>et al.</em> Computational textural mapping harmonises sampling variation and reveals multidimensional histopathological fingerprints. <em>Br J Cancer</em> 129, 683–695 (2023). </strong><a href="https://doi.org/10.1038/s41416-023-02329-4">https://doi.org/10.1038/s41416-023-02329-4</a></p> <p><strong>(2) The results shown here are in whole or part based upon data generated by the TCGA Research Network: </strong><strong><a href="https://www.cancer.gov/tcga">https://www.cancer.gov/tcga</a></strong><strong>.</strong></p>
PMF-LP: the first 10 m plastic-mulched farmland distribution map (2019-2021) in the Loess Plateau of China generated using training sample generation and classifier transfer method
<p>This dataset provides 10-m resolution plastic-mulched farmland distribution map in the Loess Plateau of China from 2019 to 2021</p> <p>*** The data file is in ".tif" format</p> <p>*** Temporal resolution: Annually</p> <p>*** Temporal coverage: 2019-2021</p> <p>*** Pixel size: 10 m</p> <p>*** Projection information: EPSG: 4326</p> <p>*** Values: 1 denotes plastic-mulched farmland (PMF) and 0 denotes non-plastic-mulched farmland (non-PMF)</p>
Lotus2 on Mycorrhizal Fungi in the Galaxy Training Network - Sample files for creating Mapping TSV
<p>Sample files for the last step on creating a Mapping TSV in the Galaxy Training Network tutorial on "Identifying Mycorrhizal Fungi from ITS2 sequencing using LotuS2"</p>
Fine Tune, Sample of Training Set
Open the record for dataset details and reuse information.
Detection of SARS-CoV-2 variants by genomic analysis of wastewater ampliconic samples (Galaxy Training Material)
<p>The tutorial aims to train how to run workflows to analyze lineages abundances in SAR-CoV-2 wastewater ampliconic samples. (https://training.galaxyproject.org/training-material/)</p>
Detection of SARS-CoV-2 variants by genomic analysis of wastewater metatranscriptomic samples (Galaxy Training Material)
<p>The tutorial aims to train how to run workflows to analyze lineages abundances in SAR-CoV-2 wastewater metatranscriptomic samples. (https://training.galaxyproject.org/training-material/)</p>
Machine-guided path sampling to discover mechanisms of molecular self-organization (Training and validation data)
<p>Training and validation data for the Nature Computational Science manuscript "Machine-guided path sampling to discover mechanisms of molecular self-organization"</p>
SARS-CoV-2 Viral Samples and Reference Genome for Galaxy Training Network SARS with Galaxy on AnVIL Tutorial
<p>In the lab activity, we'll see if there are genomic differences in the collected sample compared to the original SARS-CoV-2 genome (the reference). We need three files to do this:</p> <ul> <li><strong>SARS-CoV-2_reference_genome.fasta</strong> : the reference genome</li> <li><strong>VA_sample_forward_reads.fastq.gz</strong>: 1 of 2 raw read data files</li> <li><strong>VA_sample_reverse_reads.fastq.gz</strong>: 2 of 2 raw read data files</li> </ul> <p>The sample for this activity was derived from data collected at Virginia Commonwealth University in Richmond, VA. The researchers collected the sample with the goal of being able to track the spread and evolution of this virus state-wide, nationally, and internationally. You can download the original data <a href="https://www.ncbi.nlm.nih.gov/sra/?term=XGTK449087">here</a>.</p> <p>You can download the reference genome <a href="https://www.ncbi.nlm.nih.gov/nuccore/1798174254">here</a>.</p>
Structure preserving adversarial generation of labeled training samples for single cell segmentation
<p>Supplementary package (dataset, generated data and code) for the article: "<strong>Structure preserving adversarial generation of labeled training samples for single cell segmentation</strong>". (Cell Reports Methods, 2023 - under submission)</p> <p>Content of the package:</p> <ul> <li>datasets.zip: the images and annotations for the fallopian tube and salivary gland dataset.</li> <li>mask_quality_experiment.zip: the generated masks using SIMCEP and the generated microscopy images using pix2pix using the SIMCEP masks.</li> <li>pix2pix_models.zip: the models for fold 0 for both datasets. It can be used to synthesize new images.</li> <li>StyleGAN2-ada_models.zip: the models for synthesizing new masks.</li> <li>code.zip: a github repository (named .git) for executing the pipeline.</li> </ul>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.